Cultural advice

The Australian National University acknowledges, celebrates and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work, and whose cultures are among the oldest continuing cultures in human history.

Aboriginal and Torres Strait Islander peoples are advised that ANU Library collections may include images, names, voices, and other representations of deceased persons.

Material in the collection may contain terms, language or views that reflect the period in which the item was created and may be considered inappropriate today.

Feature Markov Decision Processes

Date

Authors

Hutter, Marcus

Publisher

Atlantis Press

Abstract

General purpose intelligent learning agents cycle through (complex,non-MDP) sequences of observations, actions, and rewards. On the other hand, reinforcement learning is well-developed for small finite state Markov Decision Processes (MDPs). So far it is

Keywords

Keywords: Dynamic Bayesian network; Finite state; General purpose; Intelligent learning; Markov Decision Processes; Objective criteria; State representation; Bayesian networks; Inference engines; Intelligent agents; Markov processes; Reinforcement; Learning algorit

URI

http://hdl.handle.net/1885/58168

Collections

ANU Research Publications

Source

Advances in Intelligent Systems Research: Proceedings of the 2nd Conference on Artificial General Intelligence (AGI 2009)

Type

Conference paper

DOI

10.2991/agi.2009.30

Restricted until

2037-12-31

Downloads

File

Description

01_Hutter_Feature_Markov_Decision_2009.pdf (420.46 KB)

02_Hutter_Feature_Markov_Decision_2009.pdf (37.49 KB)

03_Hutter_Feature_Markov_Decision_2009.pdf (55.8 KB)

04_Hutter_Feature_Markov_Decision_2009.pdf (55.32 KB)